Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Zhi Xu

A Peek Into the Reasoning of Neural Networks: Interpreting with Structural Visual Concepts


May 01, 2021
Yunhao Ge, Yao Xiao, Zhi Xu, Meng Zheng, Srikrishna Karanam, Terrence Chen, Laurent Itti, Ziyan Wu

* CVPR 2021 

  Access Paper or Ask Questions

PerSim: Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents via Personalized Simulators


Mar 17, 2021
Anish Agarwal, Abdullah Alomar, Varkey Alumootil, Devavrat Shah, Dennis Shen, Zhi Xu, Cindy Yang


  Access Paper or Ask Questions

Rethinking the Value of Labels for Improving Class-Imbalanced Learning


Jun 13, 2020
Yuzhe Yang, Zhi Xu


  Access Paper or Ask Questions

Sample Efficient Reinforcement Learning via Low-Rank Matrix Estimation


Jun 11, 2020
Devavrat Shah, Dogyoon Song, Zhi Xu, Yuzhe Yang


  Access Paper or Ask Questions

Stable Reinforcement Learning with Unbounded State Space


Jun 08, 2020
Devavrat Shah, Qiaomin Xie, Zhi Xu


  Access Paper or Ask Questions

On Reinforcement Learning for Turn-based Zero-sum Markov Games


Feb 25, 2020
Devavrat Shah, Varun Somani, Qiaomin Xie, Zhi Xu


  Access Paper or Ask Questions

Harnessing Structures for Value-Based Planning and Reinforcement Learning


Sep 26, 2019
Yuzhe Yang, Guo Zhang, Zhi Xu, Dina Katabi


  Access Paper or Ask Questions

ME-Net: Towards Effective Adversarial Robustness with Matrix Estimation


May 28, 2019
Yuzhe Yang, Guo Zhang, Dina Katabi, Zhi Xu

* ICML 2019 

  Access Paper or Ask Questions

On Reinforcement Learning Using Monte Carlo Tree Search with Supervised Learning: Non-Asymptotic Analysis


Apr 12, 2019
Devavrat Shah, Qiaomin Xie, Zhi Xu


  Access Paper or Ask Questions

Machine Learning in Cyber-Security - Problems, Challenges and Data Sets


Dec 19, 2018
Idan Amit, John Matherly, William Hewlett, Zhi Xu, Yinnon Meshi, Yigal Weinberger

* The AAAI-19 Workshop on Engineering Dependable and Secure Machine Learning Systems The AAAI-19 Workshop on Engineering Dependable and Secure Machine Learning Systems, January 28 2019, https://sites.google.com/view/edsmls2019/ 

  Access Paper or Ask Questions

Private Sequential Learning


Jun 01, 2018
John N. Tsitsiklis, Kuang Xu, Zhi Xu

* Accepted for presentation at COLT 2018 

  Access Paper or Ask Questions

Robust GANs against Dishonest Adversaries


Feb 27, 2018
Zhi Xu, Chengtao Li, Stefanie Jegelka


  Access Paper or Ask Questions